Krishna2056/Francis-Turbine-Runner-Design-and-Optimization-using-Artificial-Neural-Network-and-Genetic-Algorithm

This project uses the BOVET method to design the preliminary runner design. This design is parametrized, and these design parameters are varied to generate a Design of Experiment. To create initial data samples for Neural Network training, all the design samples in DoE are then simulated using a CFD solver, and their performance parameters are calculated. The thus formed database is then used for optimization using a Genetic Algorithm coupled with the Multi Layer Perceptron.

语言：MATLAB · GitHub 星标：4 · Fork：1

在 GitHub 上查看原仓库